Kim Haedong, Yang Hui
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:5860-5863. doi: 10.1109/EMBC44109.2020.9176465.
This paper examines county-level characteristic factors contributing to opioid-related overdose deaths in the United States. We categorized factors into three groups: demographic, socio-economic, and health care environmental group. These features were used as predictors to model the overdose deaths from all types of opioids including prescription (e.g., oxycodone and hydrocodone) and illicit opioids (e.g., heroin and fentanyl) to investigate general trend, as well as separate models for heroin and fentanyl. Multilevel mixed-effect regression was adopted to adequately model grouping effect across counties.
本文研究了美国县级层面导致阿片类药物过量死亡的特征因素。我们将这些因素分为三组：人口统计学因素、社会经济因素和医疗保健环境因素。这些特征被用作预测指标，对包括处方类阿片（如羟考酮和氢可酮）和非法阿片（如海洛因和芬太尼）在内的所有类型阿片类药物导致的过量死亡情况进行建模，以研究总体趋势，同时也分别对海洛因和芬太尼建立模型。采用多层混合效应回归来充分模拟各县之间的分组效应。
